© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 120049
    Prev
    Next
    INDEX
    Explanations

    numbers and counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -1.93
     seinem
    -1.74
    </h3>
    -1.72
     коммента
    -1.66
     zwanzig
    -1.63
    年
    -1.59
     aga
    -1.49
     ブラウス
    -1.48
    比较好
    -1.45
    AutoresizingMask
    -1.43
    POSITIVE LOGITS
    </b>
    2.13
    }$
    1.73
    ```
    1.70
    ků
    1.65
     this
    1.63
     as
    1.59
    lepší
    1.56
     our
    1.54
     शुर
    1.52
    ſelves
    1.49
    Activations Density 0.005%

    No Known Activations